lifelog

生活记录自动化系统。自动识别消息中的日期（今天/昨天/前天/具体日期），使用 SubAgent 智能判断，记录到 Notion 对应日期，每次都是**追加记录**而非覆盖。适用于：(1) 用户分享日常生活点滴时自动记录；(2) 定时自动汇总分析并填充情绪、事件、位置、人员字段

3,880 stars

byopenclaw

View on GitHub Installation ↓

Best use case

lifelog is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Teams using lifelog should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/lifelog/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/421zuoduan/lifelog/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/lifelog/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How lifelog Compares

Feature / Agent	lifelog	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

Best AI Skills for Claude

Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.

AI Agents for Marketing

Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.

AI Agents for Startups

Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.

SKILL.md Source

# LifeLog 生活记录系统

自动将用户的日常生活记录到 Notion，支持智能日期识别和自动汇总分析。

## ⚠️ 必需凭据

使用本技能前，必须设置以下环境变量：

```bash
export NOTION_KEY="your-notion-integration-token"
export NOTION_DATABASE_ID="your-notion-database-id"
```

获取方式：
1. 访问 https://www.notion.so/my-integrations 创建 Integration
2. 获取 Internal Integration Token
3. 创建 Database 并 Share 给 Integration
4. 从 URL 中提取 Database ID

# LifeLog 生活记录系统

自动将用户的日常生活记录到 Notion，支持智能日期识别和自动汇总分析。

## 核心功能

1. **实时记录** - 用户分享生活点滴时自动记录到 Notion
2. **智能日期识别（SubAgent）** - 使用 AI SubAgent 智能判断日期，优先分析文本中的日期关键词，其次分析上下文
3. **追加记录** - 每次都是追加到 Notion 指定日期的记录中，**绝不覆盖**
4. **自动汇总** - 每天凌晨自动运行 LLM 分析，生成情绪状态、主要事件、位置、人员

## Notion 数据库要求

创建 Notion Database，需包含以下字段（全部为 rich_text 类型）：

| 字段名 | 类型 | 说明 |
|--------|------|------|
| 日期 | title | 日期，如 2026-02-22 |
| 原文 | rich_text | 原始记录内容 |
| 情绪状态 | rich_text | LLM 分析后的情绪描述 |
| 主要事件 | rich_text | LLM 分析后的事件描述 |
| 位置 | rich_text | 地点列表 |
| 人员 | rich_text | 涉及的人员 |

## 记录流程

### 每条消息的处理步骤

1. 用户发送生活记录消息
2. **立即调用 SubAgent 判断日期** - 分析消息中的日期关键词（今天/昨天/前天/具体日期）和上下文，输出判断的日期（YYYY-MM-DD）
3. 调用 `lifelog-append.sh "消息内容" "判断的日期"` → 追加到 Notion 指定日期
4. 如果指定日期已有记录，则**追加**内容到该日期的原文字段中

### SubAgent 日期判断 Prompt

```
分析以下用户消息，判断它描述的是哪个日期的生活记录。

消息内容：「用户消息原文」

请输出：
1. 判断的日期（格式：YYYY-MM-DD）
2. 判断依据（简单说明）

只输出这两项，不要多余内容。
```

### 脚本用法

```bash
# 追加记录到指定日期（SubAgent 判断日期后调用）
bash lifelog-append.sh "消息内容" "YYYY-MM-DD"
```

> 注意：脚本第二个参数为日期，不传则默认为今天。每条记录都是**追加**而非覆盖。

### 2. lifelog-daily-summary-v5.sh

拉取指定日期的原文，用于 LLM 分析：

```bash
# 拉取昨天
bash lifelog-daily-summary-v5.sh

# 拉取指定日期
bash lifelog-daily-summary-v5.sh 2026-02-22
```

输出格式：
```
PAGE_ID=xxx
---原文开始---
原文内容
---原文结束---
```

### 3. lifelog-update.sh

将 LLM 分析结果写回 Notion：

```bash
bash lifelog-update.sh "<page_id>" "<情绪状态>" "<主要事件>" "<位置>" "<人员>"
```

## 配置步骤

1. 创建 Notion Integration 并获取 API Key
2. 创建 Database 并共享给 Integration
3. 获取 Database ID（URL 中提取）
4. 设置环境变量：

```bash
export NOTION_KEY="your-notion-integration-token"
export NOTION_DATABASE_ID="your-database-id"
```

## 定时任务（可选）

每天凌晨 5 点自动汇总昨天数据：

```bash
openclaw cron add \
  --name "LifeLog-每日汇总" \
  --cron "0 5 * * *" \
  --tz "Asia/Shanghai" \
  --session isolated \
  --message "运行 LifeLog 每日汇总" \
  --delivery-mode announce \
  --channel qqbot \
  --to "<用户ID>"
```

## 工作流

1. 用户发送生活记录 → 调用 SubAgent 判断日期 → 调用 `lifelog-append.sh` → **追加**到 Notion
2. 定时任务触发 → 调用 `lifelog-daily-summary-v5.sh` → 拉取原文
3. LLM 分析原文 → 调用 `lifelog-update.sh` → 填充分析字段

Related Skills

---

3891

from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891

from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891

from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891

from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891

from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891

from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891

from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891

from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891

from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure